AI Paper Atlas

Research map / Detection and segmentation / Tracking

Where and What: Long-Term Object Tracking in Egocentric Videos

Jacob Chalk, Saptarshi Sinha, Dima Damen, Yannis Kalantidis, Diane Larlus

ECCV 2026 · Detection and segmentation › Tracking · approach: Memory and correlation-based MOT

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add appearance information (ablation)Whareformer · EPIC-KITCHENSmPCL (%): 34.0 -> 72.2Improved
add location information (ablation)Whareformer · EPIC-KITCHENSmPCL (%): 62.6 -> 72.2Improved
add New Track token (ablation)Whareformer · EPIC-KITCHENSmPCL (%): 53.0 -> 72.2Improved
learn the NT token instead of fixed random (ablation)Whareformer · EPIC-KITCHENSmPCL (%): 72.0 -> 72.2Improved
use DenStream clusters instead of most recent appearance (ablation)Whareformer · EPIC-KITCHENSmPCL (%): 52.9 -> 72.2Improved
use DenStream instead of infinite memory for appearance (ablation)Whareformer · EPIC-KITCHENSmPCL (%): 70.6 -> 72.2Improved
add a 1 layer transformer assignment encoder (ablation)Whareformer · EPIC-KITCHENSmPCL (%): 66.6 -> 72.2Improved
increase encoder layers from 1 to 2 (ablation)Whareformer · EPIC-KITCHENSmPCL (%): 72.2 -> 70.8Hurt
add depth alignment for 3D locations (ablation)Whareformer · EPIC-KITCHENSmPCL (%): 70.5 -> 72.2Improved
train with DAgger correction instead of teacher forcing (ablation)Whareformer · HD-EPICmPCL (%): 41.6 -> 43.6Improved
train with DAgger correction instead of teacher forcing (ablation)Whareformer · EPIC-KITCHENSmPCL (%): 72.2 -> 71.0Hurt
replace LMK with WhareformerLMK · IT3DEgomPCL (%): 31.0 -> 58.1Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy